R1-1776

@article{guo2025deepseek,4 title={Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning}, author={Guo, Daya and Yang, Dejian and Zhang, Haowei and Song, Junxiao and Zhang, Ruoyu and Xu, Runxin and Zhu, Qihao and Ma, Shirong and Wang, Peiyi and Bi, Xiao and others}, journal={arXiv preprint arXiv:2501.12948}, year={2025} }